{"total":31,"rows":[{"id":"2006.16668","title":"GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding","created":"2020-06-30","cited_by_count":1631,"area":"moe"},{"id":"2405.04434","title":"DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model","created":"2024-05-07","cited_by_count":1135,"area":"moe"},{"id":"2606.19348","title":"DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence","created":"2026-04-26","cited_by_count":1040,"area":"moe"},{"id":"2401.06066","title":"DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models","created":"2024-01-11","cited_by_count":867,"area":"moe"},{"id":"2502.16982","title":"Muon is Scalable for LLM Training","created":"2025-02-24","cited_by_count":428,"area":"moe"},{"id":"2202.08906","title":"ST-MoE: Designing Stable and Transferable Sparse Expert Models","created":"2022-02-17","cited_by_count":399,"area":"moe"},{"id":"2409.02060","title":"OLMoE: Open Mixture-of-Experts Language Models","created":"2024-09-03","cited_by_count":301,"area":"moe"},{"id":"2505.09343","title":"Insights into DeepSeek-V3: Scaling Challenges and Reflections on Hardware for AI Architectures","created":"2025-05-14","cited_by_count":39,"area":"moe"},{"id":"2608.30320","title":"On the Design of Qwen3.8-Next Architecture: Evaluation, Efficiency, and Training Stability","created":"2026-08-31","cited_by_count":35,"area":"moe"},{"id":"2312.07987","title":"SwitchHead: Accelerating Transformers with Mixture-of-Experts Attention","created":"2023-12-13","cited_by_count":34,"area":"moe"},{"id":"2505.00315","title":"Mixture of Sparse Attention: Content-Based Learnable Sparse Attention via Expert-Choice Routing","created":"2025-05-01","cited_by_count":14,"area":"moe"},{"id":"2501.15316","title":"ToMoE: Converting Dense Large Language Models to Mixture-of-Experts through Dynamic Structural Pruning","created":"2025-01-25","cited_by_count":10,"area":"moe"},{"id":"2508.21706","title":"Accelerating Mixture-of-Experts Inference by Hiding Offloading Latency with Speculative Decoding","created":"2025-08-29","cited_by_count":8,"area":"moe"},{"id":"2510.04476","title":"Compressed Convolutional Attention: Efficient Attention in a Compressed Latent Space","created":"2025-10-06","cited_by_count":5,"area":"moe"},{"id":"2507.15465","title":"Rethinking LLM Inference Bottlenecks: Insights from Latent Attention and Mixture-of-Experts","created":"2025-07-21","cited_by_count":4,"area":"moe"},{"id":"2607.14530","title":"xHC: Expanded Hyper-Connections","created":"2026-07-16","cited_by_count":4,"area":"moe"},{"id":"2505.08944","title":"Toward Cost-Efficient Serving of Mixture-of-Experts with Asynchrony","created":"2025-05-13","cited_by_count":3,"area":"moe"},{"id":"2507.09955","title":"DeepSeek: Paradigm Shifts and Technical Evolution in Large AI Models","created":"2025-07-14","cited_by_count":3,"area":"moe"},{"id":"2607.12696","title":"Less Experts, Faster Decoding: Cost-Aware Speculative Decoding for Mixture-of-Experts","created":"2026-07-14","cited_by_count":3,"area":"moe"},{"id":"2601.01310","title":"Making MoE-based LLM Inference Resilient with Tarragon","created":"2026-01-04","cited_by_count":2,"area":"moe"},{"id":"2606.20945","title":"Grouped Query Experts: Mixture-of-Experts on GQA Self-Attention","created":"2026-06-18","cited_by_count":2,"area":"moe"},{"id":"2606.24506","title":"CrossPool: Efficient Multi-LLM Serving for Cold MoE Models through KV-Cache and Weight Disaggregation","created":"2026-06-23","cited_by_count":1,"area":"moe"},{"id":"2609.22156","title":"The Limits of Speculation: Bounding Speculative Decoding in Mixture-of-Experts","created":"2026-08-26","cited_by_count":1,"area":"moe"},{"id":"2601.21866","title":"MoHETS: Long-term Time Series Forecasting with Mixture-of-Heterogeneous-Experts","created":"2026-01-29","cited_by_count":0,"area":"moe"},{"id":"2603.10031","title":"Architecture-Aware LLM Inference Optimization on AMD Instinct GPUs: A Comprehensive Benchmark and Deployment Study","created":"2026-02-27","cited_by_count":0,"area":"moe"},{"id":"2603.20492","title":"AE-LLM: Adaptive Efficiency Optimization for Large Language Models","created":"2026-03-20","cited_by_count":0,"area":"moe"},{"id":"2605.18848","title":"Exact Linear Attention","created":"2026-05-13","cited_by_count":0,"area":"moe"},{"id":"2607.06601","title":"TriRoute: Unified Learned Routing for Joint Adaptive Attention, Experts, and KV-Cache Allocation","created":"2026-07-07","cited_by_count":0,"area":"moe"},{"id":"2608.14333","title":"Beyond Capacity: Scalable MoE LLM Inference via High-Bandwidth Flash with Direct GPU and HBM Paths","created":"2026-08-14","cited_by_count":0,"area":"moe"},{"id":"2609.36301","title":"MoRE: Scaling mixture of experts with hardware-aware low-rank routing","created":"2026-09-28","cited_by_count":0,"area":"moe"},{"id":"2610.17959","title":"Virtual Head Attention","created":"2026-10-13","cited_by_count":0,"area":"moe"}],"next_cursor":null}